A computer-implemented technique is described herein for extracting facts from unstructured text documents provided by one or more information sources. The technique uses a pipeline to perform this operation that involves, at least in part, providing a corpus of information items, extracting candidate facts from the information items, merging synonymous argument values associated with the candidate facts, organizing the candidate facts into relation clusters, and assessing the confidence level of the candidate facts within the relation clusters.
Legal claims defining the scope of protection, as filed with the USPTO.
4. The system of claim 1, wherein the text and the other text comprise freeform text.
7. The system of claim 1, wherein respective final extracted relations identify first entities, second entities, and relationships between the first entities and the second entities.
9. The system of claim 8, the first information source being an online encyclopedia, the second information source comprising other web pages accessible over the World Wide Web.
14. The method of claim 12, further comprising: employing an impression log to identify the second information items.
17. The method of claim 12, wherein outputting the final extracted relations comprises adding the final extracted relations to an ontology.
18. The method of claim 17, wherein outputting the final extracted relations comprises providing the final extracted relations to one or more knowledge-consuming applications.
19. The method of claim 18, the one or more knowledge-consuming applications comprising a question answering system, a recommendation system, and a personal assistant.
20. The method of claim 12, wherein the text and the other text comprise freeform text.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 31, 2019
October 18, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.